An official website of the United States government
Deepfake speech represents a real and growing threat to systems and society. Many detectors have been created to aid in defense against speech deepfakes. While these detectors implement myriad methodologies, many rely on low-level fragments of the speech generation process. We hypothesize that breath, a higher-level part of speech, is a key component of natural speech and thus improper generation in deepfake speech is a performant discriminator. To evaluate this, we create a breath detector and leverage this against a custom dataset of online news article audio to discriminate between real/deepfake speech. Additionally, we make this custom dataset publicly available to facilitate comparison for future work. Applying our simple breath detector as a deepfake speech discriminator on in-the-wild samples allows for accurate classification (perfect 1.0 AUPRC and 0.0 EER on test data) across 33.6 hours of audio. We compare our model with the state-of-the-art SSL-wav2vec and Codecfake models and show that these complex deep learning model completely either fail to classify the same in-the-wild samples (0.72 AUPRC and 0.89 EER), or substantially lack in the computational and temporal performance compared to our methodology (37 seconds to predict a one minute sample with Codecfake vs. 0.3 seconds with our model)
more »
« less
AntiFake: Using Adversarial Audio to Prevent Unauthorized Speech Synthesis
The rapid development of deep neural networks and generative AI has catalyzed growth in realistic speech synthesis. While this technology has great potential to improve lives, it also leads to the emergence of ''DeepFake'' where synthesized speech can be misused to deceive humans and machines for nefarious purposes. In response to this evolving threat, there has been a significant amount of interest in mitigating this threat by DeepFake detection. Complementary to the existing work, we propose to take the preventative approach and introduce AntiFake, a defense mechanism that relies on adversarial examples to prevent unauthorized speech synthesis. To ensure the transferability to attackers' unknown synthesis models, an ensemble learning approach is adopted to improve the generalizability of the optimization process. To validate the efficacy of the proposed system, we evaluated AntiFake against five state-of-the-art synthesizers using real-world DeepFake speech samples. The experiments indicated that AntiFake achieved over 95% protection rate even to unknown black-box models. We have also conducted usability tests involving 24 human participants to ensure the solution is accessible to diverse populations.
more »
« less
- PAR ID:
- 10504232
- Publisher / Repository:
- ACM
- Date Published:
- Journal Name:
- Proceedings of the ACM Conference on Computer and Communications Security
- ISSN:
- 1543-7221
- ISBN:
- 9798400700507
- Page Range / eLocation ID:
- 460 to 474
- Format(s):
- Medium: X
- Location:
- Copenhagen Denmark
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Cochlear implants (CIs) allow deaf and hard-ofhearing individuals to use audio devices, such as phones or voice assistants. However, the advent of increasingly sophisticated synthetic audio (i.e., deepfakes) potentially threatens these users. Yet, this population’s susceptibility to such attacks is unclear. In this paper, we perform the first study of the impact of audio deepfakes on CI populations. We examine the use of CI-simulated audio within deepfake detectors. Based on these results, we conduct a user study with 35 CI users and 87 hearing persons (HPs) to determine differences in how CI users perceive deepfake audio. We show that CI users can, similarly to HPs, identify text-to-speech generated deepfakes. Yet, they perform substantially worse for voice conversion deepfake generation algorithms, achieving only 67% correct audio classification. We also evaluate how detection models trained on a CI-simulated audio compare to CI users and investigate if they can effectively act as proxies for CI users. This work begins an investigation into the intersection between adversarial audio and CI users to identify and mitigate threats against this marginalized group.more » « less
-
Audio deepfakes represent a rising threat to trust in our daily communications. In response to this, the research community has developed a wide array of detection techniques aimed at preventing such attacks from deceiving users. Unfortunately, the creation of these defenses has generally overlooked the most important element of the system - the user themselves. As such, it is not clear whether current mechanisms augment, hinder, or simply contradict human classification of deepfakes. In this paper, we perform the first large-scale user study on deepfake detection. We recruit over 1,200 users and present them with samples from the three most widely-cited deepfake datasets. We then quantitatively compare performance and qualitatively conduct thematic analysis to motivate and understand the reasoning behind user decisions and differences from machine classifications. Our results show that users correctly classify human audio at significantly higher rates than machine learning models, and rely on linguistic features and intuition when performing classification. However, users are also regularly misled by pre-conceptions about the capabilities of generated audio (e.g., that accents and background sounds are indicative of humans). Finally, machine learning models suffer from significantly higher false positive rates, and experience false negatives that humans correctly classify when issues of quality or robotic characteristics are reported. By analyzing user behavior across multiple deepfake datasets, our study demonstrates the need to more tightly compare user and machine learning performance, and to target the latter towards areas where humans are less likely to successfully identify threats.more » « less
-
Abstract Speech neuroprosthetics aim to provide a natural communication channel to individuals who are unable to speak due to physical or neurological impairments. Real-time synthesis of acoustic speech directly from measured neural activity could enable natural conversations and notably improve quality of life, particularly for individuals who have severely limited means of communication. Recent advances in decoding approaches have led to high quality reconstructions of acoustic speech from invasively measured neural activity. However, most prior research utilizes data collected during open-loop experiments of articulated speech, which might not directly translate to imagined speech processes. Here, we present an approach that synthesizes audible speech in real-time for both imagined and whispered speech conditions. Using a participant implanted with stereotactic depth electrodes, we were able to reliably generate audible speech in real-time. The decoding models rely predominately on frontal activity suggesting that speech processes have similar representations when vocalized, whispered, or imagined. While reconstructed audio is not yet intelligible, our real-time synthesis approach represents an essential step towards investigating how patients will learn to operate a closed-loop speech neuroprosthesis based on imagined speech.more » « less
-
An unsupervised text-to-speech synthesis (TTS) system learns to generate speech waveforms corresponding to any written sentence in a language by observing: 1) a collection of untranscribed speech waveforms in that language; 2) a collection of texts written in that language without access to any transcribed speech. Developing such a system can significantly improve the availability of speech technology to languages without a large amount of parallel speech and text data. This paper proposes an unsupervised TTS system based on an alignment module that outputs pseudo-text and another synthesis module that uses pseudo-text for training and real text for inference. Our unsupervised system can achieve comparable performance to the supervised system in seven languages with about 10-20 hours of speech each. A careful study on the effect of text units and vocoders has also been conducted to better understand what factors may affect unsupervised TTS performance. The samples generated by our models can be found at https://cactuswiththoughts.github.io/UnsupTTS-Demo, and our code can be found at https://github.com/lwang114/UnsupTTS.more » « less
